Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-09-17

We've added 63 non-merge commits during the last 12 day(s) which contain
a total of 65 files changed, 2653 insertions(+), 751 deletions(-).

The main changes are:

1) Streamline internal BPF program sections handling and
   bpf_program__set_attach_target() in libbpf, from Andrii.

2) Add support for new btf kind BTF_KIND_TAG, from Yonghong.

3) Introduce bpf_get_branch_snapshot() to capture LBR, from Song.

4) IMUL optimization for x86-64 JIT, from Jie.

5) xsk selftest improvements, from Magnus.

6) Introduce legacy kprobe events support in libbpf, from Rafael.

7) Access hw timestamp through BPF's __sk_buff, from Vadim.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (63 commits)
  selftests/bpf: Fix a few compiler warnings
  libbpf: Constify all high-level program attach APIs
  libbpf: Schedule open_opts.attach_prog_fd deprecation since v0.7
  selftests/bpf: Switch fexit_bpf2bpf selftest to set_attach_target() API
  libbpf: Allow skipping attach_func_name in bpf_program__set_attach_target()
  libbpf: Deprecated bpf_object_open_opts.relaxed_core_relocs
  selftests/bpf: Stop using relaxed_core_relocs which has no effect
  libbpf: Use pre-setup sec_def in libbpf_find_attach_btf_id()
  bpf: Update bpf_get_smp_processor_id() documentation
  libbpf: Add sphinx code documentation comments
  selftests/bpf: Skip btf_tag test if btf_tag attribute not supported
  docs/bpf: Add documentation for BTF_KIND_TAG
  selftests/bpf: Add a test with a bpf program with btf_tag attributes
  selftests/bpf: Test BTF_KIND_TAG for deduplication
  selftests/bpf: Add BTF_KIND_TAG unit tests
  selftests/bpf: Change NAME_NTH/IS_NAME_NTH for BTF_KIND_TAG format
  selftests/bpf: Test libbpf API function btf__add_tag()
  bpftool: Add support for BTF_KIND_TAG
  libbpf: Add support for BTF_KIND_TAG
  libbpf: Rename btf_{hash,equal}_int to btf_{hash,equal}_int_tag
  ...
====================

Link: https://lore.kernel.org/r/20210917173738.3397064-1-ast@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/bpf/btf.rst

@@ -85,6 +85,7 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_VAR            14      /* Variable     */
     #define BTF_KIND_DATASEC        15      /* Section      */
     #define BTF_KIND_FLOAT          16      /* Floating point       */
+    #define BTF_KIND_TAG            17      /* Tag          */
 
 Note that the type section encodes debug info, not just pure types.
 ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@@ -106,7 +107,7 @@ Each type contains the following common data::
          * "size" tells the size of the type it is describing.
          *
          * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-         * FUNC and FUNC_PROTO.
+         * FUNC, FUNC_PROTO and TAG.
          * "type" is a type_id referring to another type.
          */
         union {
@@ -465,6 +466,32 @@ map definition.
 
 No additional type data follow ``btf_type``.
 
+2.2.17 BTF_KIND_TAG
+~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+ * ``name_off``: offset to a non-empty string
+ * ``info.kind_flag``: 0
+ * ``info.kind``: BTF_KIND_TAG
+ * ``info.vlen``: 0
+ * ``type``: ``struct``, ``union``, ``func`` or ``var``
+
+``btf_type`` is followed by ``struct btf_tag``.::
+
+    struct btf_tag {
+        __u32   component_idx;
+    };
+
+The ``name_off`` encodes btf_tag attribute string.
+The ``type`` should be ``struct``, ``union``, ``func`` or ``var``.
+For ``var`` type, ``btf_tag.component_idx`` must be ``-1``.
+For the other three types, if the btf_tag attribute is
+applied to the ``struct``, ``union`` or ``func`` itself,
+``btf_tag.component_idx`` must be ``-1``. Otherwise,
+the attribute is applied to a ``struct``/``union`` member or
+a ``func`` argument, and ``btf_tag.component_idx`` should be a
+valid index (starting from 0) pointing to a member or an argument.
+
 3. BTF Kernel API
 *****************
 

arch/x86/events/intel/core.c

@@ -2143,19 +2143,19 @@ static __initconst const u64 knl_hw_cache_extra_regs
  * However, there are some cases which may change PEBS status, e.g. PMI
  * throttle. The PEBS_ENABLE should be updated where the status changes.
  */
-static void __intel_pmu_disable_all(void)
+static __always_inline void __intel_pmu_disable_all(bool bts)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
-	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+	if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
 }
 
-static void intel_pmu_disable_all(void)
+static __always_inline void intel_pmu_disable_all(void)
 {
-	__intel_pmu_disable_all();
+	__intel_pmu_disable_all(true);
 	intel_pmu_pebs_disable_all();
 	intel_pmu_lbr_disable_all();
 }
@@ -2186,6 +2186,49 @@ static void intel_pmu_enable_all(int added)
 	__intel_pmu_enable_all(added, false);
 }
 
+static noinline int
+__intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries,
+				  unsigned int cnt, unsigned long flags)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	intel_pmu_lbr_read();
+	cnt = min_t(unsigned int, cnt, x86_pmu.lbr_nr);
+
+	memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt);
+	intel_pmu_enable_all(0);
+	local_irq_restore(flags);
+	return cnt;
+}
+
+static int
+intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+
+	/* must not have branches... */
+	local_irq_save(flags);
+	__intel_pmu_disable_all(false); /* we don't care about BTS */
+	__intel_pmu_pebs_disable_all();
+	__intel_pmu_lbr_disable();
+	/*            ... until here */
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+}
+
+static int
+intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+
+	/* must not have branches... */
+	local_irq_save(flags);
+	__intel_pmu_disable_all(false); /* we don't care about BTS */
+	__intel_pmu_pebs_disable_all();
+	__intel_pmu_arch_lbr_disable();
+	/*            ... until here */
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+}
+
 /*
  * Workaround for:
  *   Intel Errata AAK100 (model 26)
@@ -2929,7 +2972,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	intel_bts_disable_local();
 	cpuc->enabled = 0;
-	__intel_pmu_disable_all();
+	__intel_pmu_disable_all(true);
 	handled = intel_pmu_drain_bts_buffer();
 	handled += intel_bts_interrupt();
 	status = intel_pmu_get_status();
@@ -6283,9 +6326,21 @@ __init int intel_pmu_init(void)
 			x86_pmu.lbr_nr = 0;
 	}
 
-	if (x86_pmu.lbr_nr)
+	if (x86_pmu.lbr_nr) {
 		pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
 
+		/* only support branch_stack snapshot for perfmon >= v2 */
+		if (x86_pmu.disable_all == intel_pmu_disable_all) {
+			if (boot_cpu_has(X86_FEATURE_ARCH_LBR)) {
+				static_call_update(perf_snapshot_branch_stack,
+						   intel_pmu_snapshot_arch_branch_stack);
+			} else {
+				static_call_update(perf_snapshot_branch_stack,
+						   intel_pmu_snapshot_branch_stack);
+			}
+		}
+	}
+
 	intel_pmu_check_extra_regs(x86_pmu.extra_regs);
 
 	/* Support full width counters using alternative MSR range */

arch/x86/events/intel/ds.c

@@ -1301,7 +1301,7 @@ void intel_pmu_pebs_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
-		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+		__intel_pmu_pebs_disable_all();
 }
 
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)

arch/x86/events/intel/lbr.c

@@ -228,20 +228,6 @@ static void __intel_pmu_lbr_enable(bool pmi)
 		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
 }
 
-static void __intel_pmu_lbr_disable(void)
-{
-	u64 debugctl;
-
-	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
-		wrmsrl(MSR_ARCH_LBR_CTL, 0);
-		return;
-	}
-
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-}
-
 void intel_pmu_lbr_reset_32(void)
 {
 	int i;
@@ -779,8 +765,12 @@ void intel_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users && !vlbr_exclude_host())
+	if (cpuc->lbr_users && !vlbr_exclude_host()) {
+		if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+			return __intel_pmu_arch_lbr_disable();
+
 		__intel_pmu_lbr_disable();
+	}
 }
 
 void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)

arch/x86/events/perf_event.h

@@ -1240,6 +1240,25 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
+static __always_inline void __intel_pmu_pebs_disable_all(void)
+{
+	wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+}
+
+static __always_inline void __intel_pmu_arch_lbr_disable(void)
+{
+	wrmsrl(MSR_ARCH_LBR_CTL, 0);
+}
+
+static __always_inline void __intel_pmu_lbr_disable(void)
+{
+	u64 debugctl;
+
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+}
+
 int intel_pmu_save_and_restart(struct perf_event *event);
 
 struct event_constraint *

arch/x86/net/bpf_jit_comp.c

@@ -1070,41 +1070,34 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU | BPF_MUL | BPF_K:
-		case BPF_ALU | BPF_MUL | BPF_X:
 		case BPF_ALU64 | BPF_MUL | BPF_K:
-		case BPF_ALU64 | BPF_MUL | BPF_X:
-		{
-			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_2mod(0x48, dst_reg, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_2mod(0x40, dst_reg, dst_reg));
 
-			if (dst_reg != BPF_REG_0)
-				EMIT1(0x50); /* push rax */
-			if (dst_reg != BPF_REG_3)
-				EMIT1(0x52); /* push rdx */
+			if (is_imm8(imm32))
+				/* imul dst_reg, dst_reg, imm8 */
+				EMIT3(0x6B, add_2reg(0xC0, dst_reg, dst_reg),
+				      imm32);
+			else
+				/* imul dst_reg, dst_reg, imm32 */
+				EMIT2_off32(0x69,
+					    add_2reg(0xC0, dst_reg, dst_reg),
+					    imm32);
+			break;
 
-			/* mov r11, dst_reg */
-			EMIT_mov(AUX_REG, dst_reg);
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU64 | BPF_MUL | BPF_X:
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_2mod(0x48, src_reg, dst_reg));
+			else if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, src_reg, dst_reg));
 
-			if (BPF_SRC(insn->code) == BPF_X)
-				emit_mov_reg(&prog, is64, BPF_REG_0, src_reg);
-			else
-				emit_mov_imm32(&prog, is64, BPF_REG_0, imm32);
-
-			if (is64)
-				EMIT1(add_1mod(0x48, AUX_REG));
-			else if (is_ereg(AUX_REG))
-				EMIT1(add_1mod(0x40, AUX_REG));
-			/* mul(q) r11 */
-			EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
-
-			if (dst_reg != BPF_REG_3)
-				EMIT1(0x5A); /* pop rdx */
-			if (dst_reg != BPF_REG_0) {
-				/* mov dst_reg, rax */
-				EMIT_mov(dst_reg, BPF_REG_0);
-				EMIT1(0x58); /* pop rax */
-			}
+			/* imul dst_reg, src_reg */
+			EMIT3(0x0F, 0xAF, add_2reg(0xC0, src_reg, dst_reg));
 			break;
-		}
+
 			/* Shifts */
 		case BPF_ALU | BPF_LSH | BPF_K:
 		case BPF_ALU | BPF_RSH | BPF_K:

include/linux/perf_event.h

@@ -57,6 +57,7 @@ struct perf_guest_info_callbacks {
 #include <linux/cgroup.h>
 #include <linux/refcount.h>
 #include <linux/security.h>
+#include <linux/static_call.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -1612,4 +1613,26 @@ extern void __weak arch_perf_update_userpage(struct perf_event *event,
 extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr);
 #endif
 
+/*
+ * Snapshot branch stack on software events.
+ *
+ * Branch stack can be very useful in understanding software events. For
+ * example, when a long function, e.g. sys_perf_event_open, returns an
+ * errno, it is not obvious why the function failed. Branch stack could
+ * provide very helpful information in this type of scenarios.
+ *
+ * On software event, it is necessary to stop the hardware branch recorder
+ * fast. Otherwise, the hardware register/buffer will be flushed with
+ * entries of the triggering event. Therefore, static call is used to
+ * stop the hardware recorder.
+ */
+
+/*
+ * cnt is the number of entries allocated for entries.
+ * Return number of entries copied to .
+ */
+typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries,
+					   unsigned int cnt);
+DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
+
 #endif /* _LINUX_PERF_EVENT_H */

include/uapi/linux/bpf.h

@@ -1629,7 +1629,7 @@ union bpf_attr {
  * u32 bpf_get_smp_processor_id(void)
  * 	Description
  * 		Get the SMP (symmetric multiprocessing) processor id. Note that
- * 		all programs run with preemption disabled, which means that the
+ * 		all programs run with migration disabled, which means that the
  * 		SMP processor id is stable during all the execution of the
  * 		program.
  * 	Return
@@ -4877,6 +4877,27 @@ union bpf_attr {
  *		Get the struct pt_regs associated with **task**.
  *	Return
  *		A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		hardware engine is stopped shortly after the helper is
+ *		called. Therefore, the user need to filter branch entries
+ *		based on the actual use case. To capture branch trace
+ *		before the trigger point of the BPF program, the helper
+ *		should be called at the beginning of the BPF program.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *		*flags* is reserved for now and must be zero.
+ *
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-ENOENT** if architecture does not support branch records.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5076,7 @@ union bpf_attr {
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
+	FN(get_branch_snapshot),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5284,6 +5306,8 @@ struct __sk_buff {
 	__u32 gso_segs;
 	__bpf_md_ptr(struct bpf_sock *, sk);
 	__u32 gso_size;
+	__u32 :32;		/* Padding, future use. */
+	__u64 hwtstamp;
 };
 
 struct bpf_tunnel_key {